Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mitodl/agent-kit --skill code-reviewgit clone --depth 1 https://github.com/mitodl/agent-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mitodl/agent-kit/code-review)<a href="https://agentmods.dev/skills/mitodl/agent-kit/code-review"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mitodl/agent-kit/code-review"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00187 | $0.04468 |
| Opus 5.5 | $0.00075 | $0.01787 |
| Sonnet 5.5 | $0.00037 | $0.00894 |
| Haiku 4.5 | $0.00019 | $0.00447 |
Grade A, and why
code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Reviews a diff against six dimensions (correctness, goal alignment, security, simplification, efficiency, reuse) and reports findings as a severity-ordered table. Every finding is re-checked against the actual code before it ships, so the report doesn't carry a pattern-matched guess dressed up as a bug.
See references/dimensions.md for the six dimensions with worked examples of a real finding vs. a non-finding. See references/findings-format.md for the table schema and a full worked example.
Scope input
Resolve what to review from the request, in this order:
- No target given — combine three sources:
git diff(unstaged, tracked changes),git diff --staged, and untracked files. Plaingit diff/git diff --stagednever show untracked files — a working tree containing only a brand-new file looks empty to both — so checkgit status --porcelainfor??entries and include them (git add -N <file>first makes each show up as an addition in the plaingit diffwithout staging its content). Only fall back togit diff HEAD~1when all three are empty, and say explicitly that's what's being reviewed instead of silently reporting nothing. - A branch name — diff against where it forked from the default
branch, not a plain two-dot diff: detect the default branch via
git symbolic-ref refs/remotes/origin/HEAD. That ref only exists once a remote's HEAD has been set (git cloneusually does this, but a fresh/local-only repo or an unset remote won't have it — verified: a baregit initwith no remote raises "not a symbolic ref"); when it's missing, fall back togh repo view --json defaultBranchRef --jq .defaultBranchRef.nameifghand a GitHub remote are available, otherwise ask the user which branch to diff against rather than guessingmainormaster. However the default branch was found, find the merge base (git merge-base <default> <branch>), thengit diff <merge-base>...<branch>. If the request names a base branch too (a PR targeting a release branch), use that instead of the default branch. Resolve a named base against the remote, not a local branch of the same name:git fetch origin <base>, thengit merge-base origin/<base> <branch>. A localmainis often stale in a worktree, which pulls other people's commits into the diff, and a release branch often has no local copy at all. A request that names a base but no branch means the current branch (git branch --show-current) against that base, not rule 1. - A path —
git diff HEAD -- <path>(covers staged and unstaged changes to the path in one call — plaingit diff -- <path>shows only unstaged, so a fully-staged change at that path would otherwise look like an empty diff), plus the same untracked-file handling as rule 1, scoped to that path. Same default-branch detection as rule 2 if a branch was also named. - A PR number — when
ghis available and the repo has a GitHub remote,gh pr diff <number>.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 6.0 KB
- evals/files/gateway-auth/export.diff 1.1 KB
- evals/files/gateway-auth/ol-infrastructure/applications/example_reports/__main__.py 2.5 KB runs code
- evals/files/gateway-auth/pr-description.md 774 B
- references/dimensions.md 7.8 KB
- references/findings-format.md 5.6 KB
- references/ol-conventions.md 4.3 KB
- references/skeptic-brief.md 5.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +92 lines · +12 tokens per session c1380141b9d5
- 17d ago Changed · +12 lines 8aa488ef3faa
- 25d ago Changed · +83 lines · +27 tokens per session 7043c105bbf4
- 1mo ago First seen · 166 lines · 148 tokens per session scan A 6a4cb10a8ee8
code-review is a skill published in the GitHub repository mitodl/agent-kit (5 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 187 tokens to every session and 4,468 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…